{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AKVZYJEBLMLQIZMB5H5CWKFKK6","short_pith_number":"pith:AKVZYJEB","schema_version":"1.0","canonical_sha256":"02ab9c24815b17046581e9fa2b28aa57a9892e32096d9ab9f3f2295f420f8f4d","source":{"kind":"arxiv","id":"2502.10235","version":1},"attestation_state":"computed","paper":{"title":"AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Abdelhakim Benechehab, Albert Thomas, Bal\\'azs K\\'egl, Giuseppe Paolo, Maurizio Filippone, Vasilii Feofanov","submitted_at":"2025-02-14T15:46:19Z","abstract_excerpt":"Pre-trained foundation models (FMs) have shown exceptional performance in univariate time series forecasting tasks. However, several practical challenges persist, including managing intricate dependencies among features and quantifying uncertainty in predictions. This study aims to tackle these critical limitations by introducing adapters; feature-space transformations that facilitate the effective use of pre-trained univariate time series FMs for multivariate tasks. Adapters operate by projecting multivariate inputs into a suitable latent space and applying the FM independently to each dimens"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.10235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-14T15:46:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8afe0e1ce9bcf0faccb2b49d27a4248d04a8a81f78863e18e2c93cdbfae00d65","abstract_canon_sha256":"57097abb00ecb73352e76506a9f0eba59de6a09287ad11d0680f4022714c5f03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:30.401073Z","signature_b64":"qBAMqmlHz8BkxaXzKXAucBhMX9pyefYc05S5wi1QPPbT4EuTq6ohOKj1v3eePMHmQjUu7vbn20FE3bSSP1aHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02ab9c24815b17046581e9fa2b28aa57a9892e32096d9ab9f3f2295f420f8f4d","last_reissued_at":"2026-07-05T10:14:30.400578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:30.400578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Abdelhakim Benechehab, Albert Thomas, Bal\\'azs K\\'egl, Giuseppe Paolo, Maurizio Filippone, Vasilii Feofanov","submitted_at":"2025-02-14T15:46:19Z","abstract_excerpt":"Pre-trained foundation models (FMs) have shown exceptional performance in univariate time series forecasting tasks. However, several practical challenges persist, including managing intricate dependencies among features and quantifying uncertainty in predictions. This study aims to tackle these critical limitations by introducing adapters; feature-space transformations that facilitate the effective use of pre-trained univariate time series FMs for multivariate tasks. Adapters operate by projecting multivariate inputs into a suitable latent space and applying the FM independently to each dimens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10235","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.10235/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.10235","created_at":"2026-07-05T10:14:30.400640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10235v1","created_at":"2026-07-05T10:14:30.400640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10235","created_at":"2026-07-05T10:14:30.400640+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKVZYJEBLMLQ","created_at":"2026-07-05T10:14:30.400640+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKVZYJEBLMLQIZMB","created_at":"2026-07-05T10:14:30.400640+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKVZYJEB","created_at":"2026-07-05T10:14:30.400640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.04791","citing_title":"Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKVZYJEBLMLQIZMB5H5CWKFKK6","json":"https://pith.science/pith/AKVZYJEBLMLQIZMB5H5CWKFKK6.json","graph_json":"https://pith.science/api/pith-number/AKVZYJEBLMLQIZMB5H5CWKFKK6/graph.json","events_json":"https://pith.science/api/pith-number/AKVZYJEBLMLQIZMB5H5CWKFKK6/events.json","paper":"https://pith.science/paper/AKVZYJEB"},"agent_actions":{"view_html":"https://pith.science/pith/AKVZYJEBLMLQIZMB5H5CWKFKK6","download_json":"https://pith.science/pith/AKVZYJEBLMLQIZMB5H5CWKFKK6.json","view_paper":"https://pith.science/paper/AKVZYJEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10235&json=true","fetch_graph":"https://pith.science/api/pith-number/AKVZYJEBLMLQIZMB5H5CWKFKK6/graph.json","fetch_events":"https://pith.science/api/pith-number/AKVZYJEBLMLQIZMB5H5CWKFKK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKVZYJEBLMLQIZMB5H5CWKFKK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKVZYJEBLMLQIZMB5H5CWKFKK6/action/storage_attestation","attest_author":"https://pith.science/pith/AKVZYJEBLMLQIZMB5H5CWKFKK6/action/author_attestation","sign_citation":"https://pith.science/pith/AKVZYJEBLMLQIZMB5H5CWKFKK6/action/citation_signature","submit_replication":"https://pith.science/pith/AKVZYJEBLMLQIZMB5H5CWKFKK6/action/replication_record"}},"created_at":"2026-07-05T10:14:30.400640+00:00","updated_at":"2026-07-05T10:14:30.400640+00:00"}